Security audit

Clawdwallet

Security checks for vulnerabilities and agentic risk

Overview

This skill is for an agent-controlled crypto wallet, but it exposes very high-impact wallet setup and signing actions with weak documented safeguards.

Use this only with a dedicated low-balance wallet, a trusted local agent setup, and a reviewed pinned build. Do not paste a real recovery phrase into chat or logs, and manually verify every signing request's origin, chain, recipient, amount, and approval details before allowing the agent to sign.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:12
Finding: Unpinned Remote Repository and Dependencies Are Downloaded and Executed
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:22
Finding: Wallet Mnemonic and Signing Controls Are Sent Through an Unauthenticated Plaintext WebSocket
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill instructs users to initialize a wallet by sending a mnemonic in a JSON command without a strong warning that the seed phrase is the wallet's master secret and grants full control of funds across supported chains. Providing or handling mnemonics in agent workflows creates severe exposure through logs, prompts, telemetry, screenshots, memory retention, or interception over the WebSocket/control path.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill enables an agent to approve wallet requests and sign transactions for multiple chains, but it does not clearly warn that signatures and transfers can be irreversible and may be triggered by malicious or spoofed dApps. In this context, an agent-controlled wallet materially increases the chance of unauthorized approvals, phishing-driven signing, or silent fund loss if origin validation and human review are weak.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.